Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to historical progress and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    requencies
    -0.15
    lif
    -0.14
     Abdel
    -0.14
    itel
    -0.14
     vur
    -0.14
    odesk
    -0.14
    ught
    -0.14
    .tie
    -0.13
    ultiply
    -0.13
    pes
    -0.13
    POSITIVE LOGITS
     progress
    1.00
     Progress
    0.79
    progress
    0.71
    -progress
    0.66
    Progress
    0.66
     progresses
    0.64
    _progress
    0.64
    .progress
    0.59
    è¿Ľ
    0.58
     gains
    0.56
    Act Density 0.304%

    No Known Activations